Threat Advisory

New Cloud Attack Exploits Stolen Credentials to Hijack AI Resources

Threat: Malicious Campaign
Criticality: High
[subscribe_to_unlock_form]

EXECUTIVE SUMMARY

A recent security incident uncovered by the researchers has revealed a concerning new attack vector dubbed "LLMjacking." This sophisticated attack leverages stolen cloud credentials, obtained through a vulnerability in a popular Laravel version (CVE-2021-3129), to target cloud-hosted large language model (LLM) services. Unlike conventional LLM attacks focused on prompt abuse or data manipulation, LLMjacking aims to monetize access to LLM services by selling it to other cybercriminals, leaving the cloud account owner to foot the bill. The attackers meticulously probed the cloud environment, targeting LLM models hosted by various cloud providers, including AWS Bedrock, Azure, and GCP Vertex AI. Through strategic API requests and reverse proxy usage, they cleverly tested the boundaries of their access, aiming to avoid detection while maximizing their exploitation potential.[/subscribe_to_unlock_form]

EXECUTIVE SUMMARY

A recent security incident uncovered by the researchers has revealed a concerning new attack vector dubbed "LLMjacking." This sophisticated attack leverages stolen cloud credentials, obtained through a vulnerability in a popular Laravel version (CVE-2021-3129), to target cloud-hosted large language model (LLM) services. Unlike conventional LLM attacks focused on prompt abuse or data manipulation, LLMjacking aims to monetize access to LLM services by selling it to other cybercriminals, leaving the cloud account owner to foot the bill. The attackers meticulously probed the cloud environment, targeting LLM models hosted by various cloud providers, including AWS Bedrock, Azure, and GCP Vertex AI. Through strategic API requests and reverse proxy usage, they cleverly tested the boundaries of their access, aiming to avoid detection while maximizing their exploitation potential.[emaillocker id="1283"]

In their technical analysis, researchers delve into the intricate methods employed by the attackers to navigate the cloud environment. By issuing seemingly legitimate API requests with intentionally flawed parameters, the attackers probed the availability and activity of LLM services without triggering alarms. For instance, by setting the "max_tokens_to_sample" parameter to an invalid value, they confirmed both access to LLMs and their active status. Moreover, the attackers demonstrated interest in the configuration of the targeted services, indicating a sophisticated understanding of cloud infrastructure.

In conclusion, the LLMjacking attack underscores the evolving landscape of cloud security threats, emphasizing the critical importance of robust defense measures. With cloud credentials becoming a lucrative target for cybercriminals, proactive vulnerability management, secrets management, and comprehensive security posture management (CSPM/CIEM) are imperative. Cloud vendors offer a range of tools and best practices to mitigate such risks, but it ultimately falls upon organizations to implement and maintain a secure cloud environment. By staying vigilant and leveraging industry best practices, businesses can effectively safeguard their data and services against emerging threats like LLMjacking.

THREAT PROFILE:

Tactic Technique Id Technique
Initial Access T1190 Exploit Public-Facing Application
Persistence T1098 Account Manipulation
Defense Evasion T1564 Hide Artifacts
Credential Access T1003 OS Credential Dumping
Discovery T1526 Cloud Service Discovery
Collection T1530 Data from Cloud Storage
Command and Control T1090 Proxy
Impact T1496 Resource Hijacking
T1499 Endpoint Denial of Service

REFERENCES:

The following reports contain further technical details:
https://thehackernews.com/2024/05/researchers-uncover-llmjacking-scheme.html

[/emaillocker]
crossmenu